3/30/2026
NRR-Phi: Text-to-State Mapping for Ambiguity Preservation in LLM Inference
Framework addressing LLM's tendency to collapse ambiguous inputs prematurely by mapping text to non-collapsing state spaces for better dialogue reasoning.
3/30/2026
AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations
Study introducing VAPT toolkit to evaluate how LLMs extract, embody, and explain human values from conversations through user perception research.
3/30/2026
EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions
Benchmark for evaluating multimodal LLMs on handwritten STEM student solutions with mathematical formulas and diagrams, addressing authentic domain-specific evaluation gaps.
3/30/2026
TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling
TernaryLM: Language model trained natively with 1.5-bit quantization achieving memory-efficient deployment on edge devices while maintaining language modeling capability.
3/30/2026
PISCO: Precise Video Instance Insertion with Sparse Control
Video generation model for precise instance insertion with sparse control in filmmaking applications, moving beyond prompt-engineering toward controllable generation.
3/30/2026
SWE Context Bench: A Benchmark for Context Learning in Coding
Benchmark evaluating LLM-based coding agents on their ability to learn from context and reuse experience across related software engineering tasks in repositories.
3/30/2026
Administrative Law's Fourth Settlement: AI and the Capability-Accountability Trap
Administrative law analysis of how government agencies balance technological capability with democratic oversight and accountability mechanisms.
3/30/2026
The Effective Depth Paradox: Evaluating the Relationship between Architectural Topology and Trainability in Deep CNNs
Comparative study of CNN architectures (VGG, ResNet, GoogLeNet) analyzing relationship between depth and trainability in image recognition.
3/30/2026
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
DUET-VLM: dual-stage token reduction framework for vision-language models reducing computational cost while maintaining accuracy during training and inference.
3/30/2026
PedaCo-Gen: Scaffolding Pedagogical Agency in Human-AI Collaborative Video Authoring
PedaCo-Gen: pedagogically-informed human-AI system for collaborative instructional video generation using Cognitive Theory of Multimedia Learning.
3/30/2026
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
Layer gradient analysis method for identifying optimal layers in LLMs for knowledge editing while preserving model behavior on unrelated inputs.
3/30/2026
Towards single-shot coherent imaging via overlap-free ptychography
Extension of ptychographic imaging to overlap-free single-shot coherent diffractive imaging using physics-informed neural networks.
3/30/2026
SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints
SpotIt+: open-source verification tool for Text-to-SQL evaluation using bounded equivalence checking and constraint-mining for practical query discrepancies.
3/30/2026
DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization
DiFlowDubber: two-stage approach for automated video dubbing using discrete flow matching for expressive prosody and precise audio-visual synchronization.
3/30/2026
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
Method for measuring physical frame rate from visual dynamics in generative video models to improve temporal consistency.
3/30/2026
AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems
AgentTrace: lightweight framework for post-hoc root cause analysis in deployed multi-agent systems using causal graph tracing from execution logs.
3/30/2026
To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
Study showing LLMs struggle with private library code generation despite API documentation; proposes teaching methods for private-library-oriented code generation.
3/30/2026
MLLM-based Textual Explanations for Face Comparison
Analysis of multimodal LLMs generating natural language explanations for face verification decisions on unconstrained images.
3/30/2026
Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification
Goedel-Code-Prover: hierarchical proof search framework for automated code verification in Lean 4 using LLMs to decompose complex verification goals.
3/30/2026
Modernizing Amdahl's Law: How AI Scaling Laws Shape Computer Architecture
Analysis of how AI scaling laws reshape classical Amdahl's Law for modern heterogeneous computer architectures with specialized accelerators and tensor datapaths.
3/30/2026
KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning
KG-Hopper: reinforcement learning framework enabling compact open-source LLMs to perform knowledge graph reasoning for multi-hop KBQA tasks.
3/30/2026
mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
mSFT: iterative algorithm for multi-task supervised fine-tuning that addresses heterogeneous overfitting by dynamically adjusting compute budget across datasets.
3/30/2026
KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training
KALAVAI: quantitative model predicting when independently trained specialist LLMs can be fused post-hoc with measurable performance gains; includes practical prediction formula.
3/30/2026
EVA: Efficient Reinforcement Learning for End-to-End Video Agent
EVA: reinforcement learning framework for video agents using MLLMs with adaptive reasoning to handle long video sequences and temporal dependencies efficiently.
3/30/2026
MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG
MDKeyChunker: structure-aware chunking pipeline for Markdown documents with single-call LLM enrichment to improve RAG accuracy and reduce metadata extraction overhead.
3/30/2026
AI Generalisation Gap In Comorbid Sleep Disorder Staging
Deep learning model for automated sleep staging shows poor generalization to clinical populations with comorbid sleep disorders; proposes iSLEEPS to address limitations.
3/30/2026
SM-Net: Learning a Continuous Spectral Manifold from Multiple Stellar Libraries
arXiv paper on SM-Net, machine learning model generating stellar spectra from fundamental stellar parameters using multiple libraries.
3/30/2026
The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation
arXiv paper analyzing response homogenization in RLHF-aligned LLMs and its effects on uncertainty estimation methods.
3/30/2026
Efficient Detection of Bad Benchmark Items with Novel Scalability Coefficients
arXiv paper introducing scalability coefficients for detecting problematic items in large-scale AI benchmarks using isotonic regression.
3/30/2026
Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields
arXiv paper on Few TensoRF, a 3D reconstruction framework combining tensor representations with few-shot learning for NeRF.
3/30/2026
Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models
arXiv paper demonstrating dual-layer side-channel attacks on local Vision-Language Models exploiting dynamic preprocessing vulnerabilities.
3/30/2026
Empowering Epidemic Response: The Role of Reinforcement Learning in Infectious Disease Control
arXiv survey on reinforcement learning applications for infectious disease control and epidemic response optimization.
3/30/2026
Pure and Physics-Guided Deep Learning Solutions for Spatio-Temporal Groundwater Level Prediction at Arbitrary Locations
arXiv paper on physics-guided deep learning for groundwater level prediction using spatio-temporal modeling.
3/30/2026
MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Training
MAGNET: decentralized system for autonomous generation and training of domain-expert language models using autoresearch and BitNet ternary quantization.
3/30/2026
A Compression Perspective on Simplicity Bias
Theoretical analysis of simplicity bias in neural networks using minimum description length principle and compression framework.
3/30/2026
In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts
Investigation of whether LLMs perform genuine in-context molecular property prediction or rely on memorization despite potential training data contamination.
3/30/2026
Why Safety Probes Catch Liars But Miss Fanatics
Analysis of activation-based probes for detecting misaligned AI systems, showing blind spots in detecting coherent misalignment versus deception.
3/30/2026
DRiffusion: Draft-and-Refine Process Parallelizes Diffusion Models with Ease
DRiffusion: parallel sampling framework accelerating diffusion model inference through draft-and-refine process with skip transitions.
3/30/2026
Data-Driven Plasticity Modeling via Acoustic Profiling
Data-driven framework using wavelet analysis on acoustic emission data to model plastic deformation in metals.
3/30/2026
Decoding Defensive Coverage Responsibilities in American Football Using Factorized Attention Based Transformer Models
Transformer model with factorized attention to predict defensive coverage assignments in NFL football plays.
3/30/2026
Parameter-Free Dynamic Regret for Unconstrained Linear Bandits
Bandit algorithm approach for dynamic regret minimization in unconstrained adversarial linear settings.
3/30/2026
Preventing Data Leakage in EEG-Based Survival Prediction: A Two-Stage Embedding and Transformer Framework
Deep learning framework using transformers to predict patient outcomes from EEG while preventing data leakage in survival prediction.
3/30/2026
Personalizing Mathematical Game-based Learning for Children: A Preliminary Study
Game-based learning system using adaptive mechanisms to personalize mathematical education for children.
3/30/2026
Online Learning for Dynamic Constellation Topologies
Machine learning for satellite network topology configuration under dynamic orbital movement.
3/30/2026
EngineAD: A Real-World Vehicle Engine Anomaly Detection Dataset
EngineAD real-world multivariate anomaly detection dataset from vehicle fleet sensor telemetry with expert annotations for safety-critical domain.
3/30/2026
Adversarial-Robust Multivariate Time-Series Anomaly Detection via Joint Information Retention
ARTA joint training framework for adversarially robust multivariate time-series anomaly detection using min-max optimization and information retention.
3/30/2026
On the Objective and Feature Weights of Minkowski Weighted k-Means
Theoretical analysis of Minkowski weighted k-means revealing objective as power-mean aggregation of within-cluster dispersions controlled by exponent.
3/30/2026
Second-Order, First-Class: A Composable Stack for Curvature-Aware Training
Somax composable Optax-native stack for second-order curvature-aware training with modular APIs for operators, estimators, and preconditioners.
3/30/2026
QuitoBench: A High-Quality Open Time Series Forecasting Benchmark
QuitoBench open benchmark for time series forecasting covering eight trend-seasonality-forecastability regimes with regime-balanced dataset design.
3/30/2026
GLU: Global-Local-Uncertainty Fusion for Scalable Spatiotemporal Reconstruction and Forecasting
GLU framework for sparse spatiotemporal reconstruction and forecasting using global-local-uncertainty fusion with unified state representation.